AI Pipeline Overview

AI Suite to 149 plików, ~22.6k LOC - największy moduł w Vista.

AI Suite Architecture

graph TB
    subgraph Frontend["AI Suite Frontend (149 files, 22.6k LOC)"]
        subgraph Engine["Engine Layer"]
            AIChatContext[AIChatContext]
            AIChatProvider[AIChatProvider]
            AssistantHostManager[AssistantHostManager]
        end

        subgraph Hosts["Host Components"]
            FloatingHost[AIFloatingHost<br/>Orb + Panel]
            SystemHost[AISystemHost<br/>Full-page]
            SpecialistHost[AISpecialistHost<br/>Visit context]
        end

        subgraph Hooks["Core Hooks"]
            useStreamingManager[useStreamingManager<br/>977 LOC]
            useUnifiedAI[useUnifiedAI<br/>439 LOC]
            useChatHistory[useChatHistory<br/>318 LOC]
            useChatSending[useChatSending<br/>380 LOC]
        end

        subgraph UI["UI Components"]
            InputArea[InputArea<br/>655 LOC]
            ChatCanvas[AIChatCanvas<br/>1,078 LOC]
            FloatingOrb[AIFloatingOrb<br/>570 LOC]
            MessageList[FloatingMessageList]
        end

        subgraph Agents["AI Agents"]
            NotesAgent[Notes Agent]
            SuggestionsAgent[Suggestions Agent]
            VoiceAgent[Voice Agent]
        end
    end

    subgraph Backend["Rust Backend (40 commands)"]
        UnifiedAI[unified_ai module]
        SOAP[soap_generation.rs<br/>24,961 LOC]
        Chat[chat/service.rs]
        VectorMemory[vector_memory/]
        Diagnostics[diagnostics.rs<br/>28,669 LOC]
    end

    Engine --> Hosts
    Hooks --> Engine
    UI --> Hooks
    Agents --> Hooks
    Hooks --> UnifiedAI

AI Rust Commands (40 total)

Category	Commands
Chat	unified_ai_chat, unified_ai_chat_stream, unified_ai_poll_response
SOAP	start_soap_generation, get_soap_generation_status, unified_ai_generate_soap
Suggestions	unified_ai_generate_suggestions, unified_ai_generate_tasks, unified_ai_generate_differential
Memory	get_vista_memory, save_vista_memory, ai_context_vault_*
Sessions	ai_chat_session_save, ai_chat_sessions_list, ai_chat_session_load
Diagnostics	diagnostics_ai_config, diagnostics_ai_curl, unified_ai_health_check

Command Distribution

pie showData
    title "Tauri Commands by Module (197 active)"
    "Visits" : 25
    "AI Suite" : 40
    "Audio" : 16
    "Patients" : 15
    "Auth" : 18
    "Tasks" : 9
    "Calendar" : 10
    "Settings" : 12
    "Analytics" : 12
    "Dictionary" : 7
    "Clinical Notes" : 5
    "Other" : 28

AI Streaming Sequence

sequenceDiagram
    participant UI as ChatPanel
    participant Hook as useStreamingManager
    participant Tauri as Tauri Events
    participant Rust as unified_ai_chat_stream

    UI->>Hook: sendMessage(text)
    Hook->>Rust: invoke('unified_ai_chat_stream', {requestId})
    Hook->>Tauri: listen('ai-stream-token:' + requestId)
    Hook->>Tauri: listen('ai-stream-complete:' + requestId)
    Hook->>Tauri: listen('ai-stream-error:' + requestId)

    loop Token streaming
        Rust->>Tauri: emit('ai-stream-token:' + requestId, token)
        Tauri-->>Hook: onToken(token)
        Hook->>UI: appendToken(token)
    end

    alt Success
        Rust->>Tauri: emit('ai-stream-complete:' + requestId)
        Tauri-->>Hook: onComplete()
        Hook->>UI: finishMessage()
    else Error
        Rust->>Tauri: emit('ai-stream-error:' + requestId, error)
        Tauri-->>Hook: onError(error)
        Hook->>UI: showError()
    end

    Hook->>Tauri: unlisten(all listeners)

Unified AI - Provider Failover

Vista implementuje zaawansowany system AI z automatycznym failover:

sequenceDiagram
    participant UI as Frontend UI
    participant UAI as Unified AI Client
    participant SR as Service Resolver
    participant LIB as LibraxisAI Cloud
    participant MLX as Local MLX
    participant OAI as OpenAI API

    UI->>UAI: AI Request (transcribe/chat/generate)
    UAI->>SR: Resolve Provider Chain

    Note over SR: Provider Priority:<br/>1. LibraxisAI<br/>2. Local MLX<br/>3. OpenAI

    SR->>LIB: Try Primary (LibraxisAI)
    alt LibraxisAI Success
        LIB->>SR: Response + Metrics
        SR->>UAI: Success
        UAI->>UI: Result
    else LibraxisAI Failure
        SR->>MLX: Try Secondary (MLX)
        alt MLX Success
            MLX->>SR: Response
            SR->>UAI: Success
            UAI->>UI: Result
        else MLX Failure
            SR->>OAI: Try Tertiary (OpenAI)
            OAI->>SR: Response
            SR->>UAI: Success
            UAI->>UI: Result
        end
    end

SOAP Generation Pipeline

Audio Recording
    ↓
Speech-to-Text (Whisper)
    ↓
Medical Context Analysis (LLM)
    ↓
SOAP Structure Generation
    ↓
Human Review & Approval